Question

我是python的新手，正在尝试从网站上抓取数据。下面的代码返回我正在寻找的信息，但是当尝试将数据导出到CSV时，它只包含DataFrame的最后一行。我认为这是因为在写入字典时，它会替换最后一行数据，但我不确定如何避免这种情况。

from bs4 import BeautifulSoup
import requests
import pandas as pd

url = "http://elite.wttstats.pointstreak.com/boxscore.html?gameid=3149470"
r = requests.get(url)
data = r.text
soup = BeautifulSoup(data)
table = soup.find_all('table', {'class' : 'table nova-stats-table table-    
striped table-hover'})[0]
tbody = table.find('tbody')
rows = tbody.find_all('tr')[1:]

hockey = []
data = {
    '#' : [],
    'name' : [],
    'G' : [],
    'A' : [],
    'PTS' : [],
    'S' : [],
    'PIM' : []
    }

for row in rows:
    cells = row.findAll('td')
    data['#'] = cells[0].find(text=True)
    data['name'] = cells[1].find('a').find(text=True).strip("\t")
    data['G'] = cells[2].find(text=True)
    data['A'] = cells[3].find(text=True)
    data['PTS'] = cells[4].find(text=True)
    data['S'] = cells[5].find(text=True)
    data['PIM'] = cells[6].find(text=True)
    hockey = pd.DataFrame([data])
    print(hockey)
    hockey.to_csv("Hockey Data.csv", columns = ["#", "name", "G", "A",         
    "PTS", "S", "PIM"])

以下是从print(hockey)返回的曲棍球DataFrame示例。

#  A  G PIM PTS  S           name
0  3  0  0   7   0  0  Stadel, Riley
#  A  G PIM PTS  S           name
0  4  0  0   0   0  0  Harding, Adam
#  A  G PIM PTS  S             name
0  10  0  0   0   0  0  Brickler, Tyler
#  A  G PIM PTS  S          name
0  11  0  0   2   0  0  Inglis, Kris
#  A  G PIM PTS  S               name
0  12  1  0   0   1  0  Lévesque, Gabriel
#  A  G PIM PTS  S            name
0  14  0  0   0   0  0  Cownie, Jordan
#  A  G PIM PTS  S                 name
0  17  1  0   0   1  0  Mimar, Marc-Olivier
#  A  G PIM PTS  S           name
0  19  0  1   0   1  0  Jensen, Jimmy
#  A  G PIM PTS  S              name
0  23  2  0   2   2  0  Andersson, Johan

Pandas仅将1行导出为CSV文件

0 个答案: